242 questions with no answers
0
votes
0
answers
186
views
how i can extract the labels from my csv file
Can any one tell me what is the error I'm using MNIST data with 400 additional images label as 10,11,13,14 when I'm extracting labels from CSV file it will give me error. As below
line 34, in ...
- 765
1
vote
0
answers
77
views
Test Accuracy and ConfMatrix dont match up?
I'm doing the "hello world" project involving the MNIST dataset. But by test accuracy doesn't seem to match with the diagonal of my confusion matrix. I'm not sure if I have a bug somewhere ...
- 765
0
votes
0
answers
70
views
Keras SKLearnClassifier wrapper can't fit MNIST data
I'm trying to use the SKLearnClassifier Keras wrapper to do some grid searching and cross validation using the sklearn library but I'm unable to get the model to work properly.
def build_model(X, y, ...
0
votes
0
answers
90
views
Error when importing to_categorical from tensorflow.keras.utils
Whenever I use
from tensorflow.keras.utils import to_categorical
or
from tensorflow.keras.datasets import mnist
I receive the error "could not be resolved". Did anything change over the ...
- 1,183
0
votes
0
answers
130
views
Gradient descent 3D visualization Python
I've recently implemented a neural network from scratch and am now focusing on visualizing the optimization process. Specifically, I'm interested in creating a 3D visualization of the loss landscape ...
- 59
1
vote
0
answers
103
views
How can I apply data augmentation to MNIST images in R's keras package?
I'm fluent in R but a total beginner with deep learning. I'm trying to splice together two bits of code from the Chollet et al. Deep Learning with R book (2d ed), namely one for a CNN model for the ...
- 35
0
votes
0
answers
187
views
options for loading mnist dataset in python
I am confused about the options for loading data into python. Using the mnist dataset, I have found numerous options for loading the test and trainsets. Since these options are tethered to the ...
CommunityBot
- 1
0
votes
0
answers
66
views
The DataLoader in PyTorch modifies my data
I am trying to train my deep network on the MNIST dataset. When I try to upload the dataset to the dataloader and get the batched data through the iterator, I get modified data that differs from the ...
- 1
0
votes
0
answers
106
views
Fixing the train-test resolution discrepancy in a YOLO model
I have trained a yolov8 model in order to detect handwritten digits on paper with MNIST dataset. The problem is that the images on the dataset are 416x416 and once the model is trained it gets really ...
0
votes
0
answers
47
views
Tensorflow model stuck at 10% accuracy on fashionmnist
I'm working on trying to implement a capsule network in tf2. However when running the code the model never exceeds an accuracy of 10% on fashionmnist and if I use the included loss function the loss ...
- 21
0
votes
0
answers
67
views
C# MNIST neural network increases to about 20% accuracy, then falls back to 10%
I've been trying to use this python MNIST code to write a neural network in C# - https://www.kaggle.com/code/wwsalmon/simple-mnist-nn-from-scratch-numpy-no-tf-keras/notebook - but after many attempts ...
- 1
0
votes
0
answers
35
views
Custom image is not being predicted correctly in MNIST neural network model from scratch
Accuracy = 92.29285714285714 % on test data but custom image is predicting incorrectly. I have tried multiple numbers. Am I doing preprocessing of custom image wrong? Or simple feedforward neural ...
0
votes
0
answers
96
views
How to update first layer weights in a neural network?
I’m trying to make a neural network without using any deep learning library that recognizes numbers in the mnist database. Its structure is: 784 input neurons, 10 hidden neurons (only 1 hidden layer) ...
- 60.9k
0
votes
0
answers
52
views
Why isn't my mnist model reading my handwritten number correctly?
I used a sequential neural network and created a simple paint app in pygame to draw an integer. It then goes to attempt a read off of that image.
This first part is my neural network file.
import os
...
- 24.5k
0
votes
0
answers
44
views
Loss increasing training neural network in R
I am trying to train a NN with the MNIST dataset in R.
Here is my code:
#Model definition
model = keras_model_sequential() %>%
layer_dense(units=512, activation="relu", input_shape = ...
